feat:Implement Gemini ASR support and remove preview routing

changelog.md

@@ -9,10 +9,12 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/).
 ### Added
 
 - **Inline REST LLM tools** — Global and CN LLM vendors now accept dictionary-based `tools` definitions and serialize them to `llm.tools`. Added public `LlmToolConfig`, `LlmToolExecutionConfig`, `LlmToolFunctionConfig`, `LlmToolFunctionParametersConfig`, and `LlmToolServerConfig` aliases. Tool execution must be enabled explicitly with `Agent.with_tools()`.
+- **Gemini ASR** — Added `GeminiSTT` to the standard AgentKit STT vendors using the Fern-generated `GeminiAsrParams` schema. It requires `api_key` and `model`; `language`, `word_timestamp`, and `sample_rate` are optional.
 
 ### Changed
 
 - **Generated filler words configuration** — Generated filler word settings are now optional. The service can use default generator settings when `generated_config` is omitted, and `llm_provider`, `prompt`, and `fallback_strategy` may be omitted individually.
+- **Gemini ASR routing** — Gemini ASR now uses the normal regional API endpoint and generated request validation. The temporary preview routing layer has been removed.
 
 ## [v2.7.2] — 2026-08-26
 

docs/concepts/vendors.md

@@ -119,6 +119,7 @@ top-level `asr.keywords`. Both vendors also accept `additional_params`, serializ
 | `DeepgramSTT` | Deepgram | `model` for Agora-managed `nova-2`/`nova-3`; `api_key` for BYOK; `language?`, `keyterm?` |
 | `MicrosoftSTT` | Microsoft Azure | `key`, `region`, `language` |
 | `OpenAISTT` | OpenAI | `api_key` |
+| `GeminiSTT` | Google Gemini | `api_key`, `model`; optional `language`, `word_timestamp`, `sample_rate` |
 | `GoogleSTT` | Google Cloud | `project_id`, `location`, `adc_credentials_string`, `language` |
 | `AmazonSTT` | Amazon Transcribe | `access_key`, `secret_key`, `region`, `language` |
 | `AssemblyAISTT` | AssemblyAI | `api_key`, `language` |
@@ -146,8 +147,6 @@ from agora_agent import DeepgramSTT
 stt = DeepgramSTT(api_key='your-deepgram-key', language='en-US', model='nova-2')
 ```
 
-> **Preview providers** — `GeminiSTT` (ASR) lives in `agora_agent.agentkit.preview`. Sessions using it route to the preview gateway automatically. See [Preview Endpoint](../guides/preview-endpoint.md).
-
 ## MLLM Vendors
 
 Used with `agent.with_mllm()` for the [MLLM flow](../guides/mllm-flow.md). These handle audio input and output end-to-end.

docs/guides/regional-routing.md

@@ -40,7 +40,7 @@ If you omit `with_stt()`, AgentKit uses `FengmingSTT` by default for `Area.CN` c
 
 | Client area | STT classes | LLM classes | MLLM classes | TTS classes | Avatar classes |
 |---|---|---|---|---|---|
-| `Area.US`, `Area.EU`, `Area.AP` | `DeepgramSTT`, `SpeechmaticsSTT`, `MicrosoftSTT`, `OpenAISTT`, `GoogleSTT`, `AmazonSTT`, `AssemblyAISTT`, `AresSTT`, `SarvamSTT`, `XaiSTT` | `OpenAI`, `AzureOpenAI`, `Anthropic`, `Gemini`, `Groq`, `VertexAILLM`, `AmazonBedrock`, `Dify`, `CustomLLM` | `OpenAIRealtime`, `AzureOpenAIRealtime`, `GeminiLive`, `VertexAI`, `XaiGrok` | `ElevenLabsTTS`, `MicrosoftTTS`, `OpenAITTS`, `CartesiaTTS`, `GoogleTTS`, `AmazonTTS`, `DeepgramTTS`, `GradiumTTS`, `MistralTTS`, `TypecastTTS`, `HumeAITTS`, `RimeTTS`, `FishAudioTTS`, `MiniMaxTTS`, `MurfTTS`, `SarvamTTS`, `GenericTTS`, `XaiTTS` | `LiveAvatarAvatar`, `HeyGenAvatar`, `AkoolAvatar`, `AnamAvatar`, `GenericAvatar` |
+| `Area.US`, `Area.EU`, `Area.AP` | `DeepgramSTT`, `SpeechmaticsSTT`, `MicrosoftSTT`, `OpenAISTT`, `GeminiSTT`, `GoogleSTT`, `AmazonSTT`, `AssemblyAISTT`, `AresSTT`, `SarvamSTT`, `XaiSTT` | `OpenAI`, `AzureOpenAI`, `Anthropic`, `Gemini`, `Groq`, `VertexAILLM`, `AmazonBedrock`, `Dify`, `CustomLLM` | `OpenAIRealtime`, `AzureOpenAIRealtime`, `GeminiLive`, `VertexAI`, `XaiGrok` | `ElevenLabsTTS`, `MicrosoftTTS`, `OpenAITTS`, `CartesiaTTS`, `GoogleTTS`, `AmazonTTS`, `DeepgramTTS`, `GradiumTTS`, `MistralTTS`, `TypecastTTS`, `HumeAITTS`, `RimeTTS`, `FishAudioTTS`, `MiniMaxTTS`, `MurfTTS`, `SarvamTTS`, `GenericTTS`, `XaiTTS` | `LiveAvatarAvatar`, `HeyGenAvatar`, `AkoolAvatar`, `AnamAvatar`, `GenericAvatar` |
 | `Area.CN` | `FengmingSTT`, `TencentSTT`, `MicrosoftCNSTT`, `XfyunSTT`, `XfyunBigModelSTT`, `XfyunDialectSTT` | `AliyunLLM`, `BytedanceLLM`, `DeepSeekLLM`, `TencentLLM` | `QwenOmni` | `MiniMaxCNTTS`, `TencentTTS`, `BytedanceTTS`, `MicrosoftCNTTS`, `CosyVoiceTTS`, `BytedanceDuplexTTS`, `StepFunTTS`, `GenericTTS` | `SenseTimeAvatar`, `SpatiusAvatar` |
 
 Global client example:

docs/index.md

@@ -53,7 +53,6 @@ The Agora Conversational AI Python SDK lets you build voice-powered AI agents on
 | [Pagination](./guides/pagination.md) | Iterate over paginated list endpoints |
 | [Advanced](./guides/advanced.md) | Raw response, retries, timeouts, custom httpx client |
 | [Low-Level API](./guides/low-level-api.md) | Generated REST APIs |
-| [Preview Endpoint](./guides/preview-endpoint.md) | Session-scoped preview routing and the `agora-feature` gate header |
 | [Client Reference](./reference/client.md) | Full `Agora` / `AsyncAgora` API |
 | [Agent Reference](./reference/agent.md) | Full `Agent` builder API |
 | [Session Reference](./reference/session.md) | Full `AgentSession` / `AsyncAgentSession` API |

docs/reference/vendors.md

@@ -20,7 +20,7 @@ Construct vendors directly from `agora_agent`, then bind a client with `Agent(cl
 
 | Area | STT classes | LLM classes | MLLM classes | TTS classes | Avatar classes |
 |---|---|---|---|---|---|
-| `Area.US`, `Area.EU`, `Area.AP` | `DeepgramSTT`, `SpeechmaticsSTT`, `MicrosoftSTT`, `OpenAISTT`, `GoogleSTT`, `AmazonSTT`, `AssemblyAISTT`, `AresSTT`, `SarvamSTT`, `XaiSTT` | `OpenAI`, `AzureOpenAI`, `Anthropic`, `Gemini`, `Groq`, `VertexAILLM`, `AmazonBedrock`, `Dify`, `CustomLLM` | `OpenAIRealtime`, `AzureOpenAIRealtime`, `GeminiLive`, `VertexAI`, `XaiGrok` | `ElevenLabsTTS`, `MicrosoftTTS`, `OpenAITTS`, `CartesiaTTS`, `GoogleTTS`, `AmazonTTS`, `DeepgramTTS`, `GradiumTTS`, `MistralTTS`, `TypecastTTS`, `HumeAITTS`, `RimeTTS`, `FishAudioTTS`, `MiniMaxTTS`, `MurfTTS`, `SarvamTTS`, `GenericTTS`, `XaiTTS` | `LiveAvatarAvatar`, `HeyGenAvatar`, `AkoolAvatar`, `AnamAvatar`, `GenericAvatar` |
+| `Area.US`, `Area.EU`, `Area.AP` | `DeepgramSTT`, `SpeechmaticsSTT`, `MicrosoftSTT`, `OpenAISTT`, `GeminiSTT`, `GoogleSTT`, `AmazonSTT`, `AssemblyAISTT`, `AresSTT`, `SarvamSTT`, `XaiSTT` | `OpenAI`, `AzureOpenAI`, `Anthropic`, `Gemini`, `Groq`, `VertexAILLM`, `AmazonBedrock`, `Dify`, `CustomLLM` | `OpenAIRealtime`, `AzureOpenAIRealtime`, `GeminiLive`, `VertexAI`, `XaiGrok` | `ElevenLabsTTS`, `MicrosoftTTS`, `OpenAITTS`, `CartesiaTTS`, `GoogleTTS`, `AmazonTTS`, `DeepgramTTS`, `GradiumTTS`, `MistralTTS`, `TypecastTTS`, `HumeAITTS`, `RimeTTS`, `FishAudioTTS`, `MiniMaxTTS`, `MurfTTS`, `SarvamTTS`, `GenericTTS`, `XaiTTS` | `LiveAvatarAvatar`, `HeyGenAvatar`, `AkoolAvatar`, `AnamAvatar`, `GenericAvatar` |
 | `Area.CN` | `FengmingSTT`, `TencentSTT`, `MicrosoftCNSTT`, `XfyunSTT`, `XfyunBigModelSTT`, `XfyunDialectSTT` | `AliyunLLM`, `BytedanceLLM`, `DeepSeekLLM`, `TencentLLM` | `QwenOmni` | `MiniMaxCNTTS`, `TencentTTS`, `BytedanceTTS`, `MicrosoftCNTTS`, `CosyVoiceTTS`, `BytedanceDuplexTTS`, `StepFunTTS`, `GenericTTS` | `SenseTimeAvatar`, `SpatiusAvatar` |
 
 Global example:
@@ -541,6 +541,28 @@ For `nova-2` and `nova-3`, omit `api_key` to use Agora-managed credentials. For
 | `model` | `str` | No | `None` | Recognition model |
 | `additional_params` | `Dict[str, Any]` | No | `None` | Additional parameters |
 
+### `GeminiSTT`
+
+| Parameter | Type | Required | Default | Description |
+|---|---|---|---|---|
+| `api_key` | `str` | Yes | — | Google Gemini API key |
+| `model` | `str` | Yes | — | Gemini transcription model, such as `gemini-3.7-transcribe-live` |
+| `language` | `str` | No | `None` | Language code for speech recognition. Takes precedence over top-level `asr.language`. |
+| `word_timestamp` | `bool` | No | `None` | Include word-level timestamps in transcription results |
+| `sample_rate` | `int` | No | `None` | Audio sample rate in Hz |
+| `additional_params` | `Dict[str, Any]` | No | `None` | Additional Gemini ASR parameters |
+
+```python
+from agora_agent import GeminiSTT
+
+stt = GeminiSTT(
+    api_key="your-google-api-key",
+    model="gemini-3.7-transcribe-live",
+    language="en-US",
+    word_timestamp=True,
+)
+```
+
 ### `AmazonSTT`
 
 | Parameter | Type | Required | Default | Description |

src/agora_agent/__init__.py

@@ -45,6 +45,7 @@
         ElevenLabsTTS,
         FishAudioTTS,
         Gemini,
+        GeminiSTT,
         GeminiLive,
         GenericAvatar,
         GenericTTS,

src/agora_agent/agentkit/__init__.py

@@ -180,6 +180,7 @@
     Dify,
     FishAudioTTS,
     Gemini,
+    GeminiSTT,
     GeminiLive,
     GenericAvatar,
     GoogleSTT,
@@ -436,6 +437,7 @@
     "MicrosoftSTT",
     "MicrosoftCNSTT",
     "OpenAISTT",
+    "GeminiSTT",
     "GoogleSTT",
     "AmazonSTT",
     "AssemblyAISTT",

src/agora_agent/agentkit/agent.py

@@ -202,34 +202,10 @@ class SessionOptions(typing_extensions.TypedDict, total=False):
     warn: typing.Callable[[str], None]
 
 
-
-def _drop_none(value: typing.Any) -> typing.Any:
-    """Recursively remove None-valued mapping entries."""
-    if isinstance(value, dict):
-        return {k: _drop_none(v) for k, v in value.items() if v is not None}
-    if isinstance(value, list):
-        return [_drop_none(item) for item in value]
-    return value
-
-
 def _start_properties_from_mapping(
     properties: typing.Mapping[str, typing.Any],
 ) -> StartAgentsRequestProperties:
-    try:
-        return parse_obj_as(StartAgentsRequestProperties, dict(properties))
-    except Exception:
-        # Preview providers are absent from the generated unions by design — the
-        # schema models what production serves. A config the preview gateway
-        # does understand is passed through unvalidated rather than rejected.
-        # Imported lazily: preview.client imports the pool client, which imports
-        # this module.
-        from .preview.client import required_preview_features
-
-        if required_preview_features(properties):
-            # The typed path serializes with exclude_none; strip None here so the
-            # bypass puts the same bytes on the wire instead of explicit nulls.
-            return typing.cast(StartAgentsRequestProperties, _drop_none(dict(properties)))
-        raise
+    return parse_obj_as(StartAgentsRequestProperties, dict(properties))
 
 
 # LLM sub-type aliases
@@ -1051,10 +1027,6 @@ def to_properties(
         if is_mllm_mode:
             if self._mllm is not None:
                 mllm_config = dict(self._mllm)
-                # These are production wire spellings. A route that spells one of them
-                # differently needs a rename entry in `preview/client.py`, or the value
-                # lands in a field the provider ignores and fails silently. See
-                # docs/guides/preview-endpoint.md#the-vendor-class-is-not-the-whole-wire-shape.
                 if self._greeting is not None:
                     mllm_config.setdefault("greeting_message", self._greeting)
                 if self._failure_message is not None:
@@ -1123,10 +1095,6 @@ def _resolve_asr_config(self, turn_detection_config: TurnDetectionInput) -> typi
         if not asr_config:
             area_scope = getattr(self._client, "area_scope", None)
             asr_config["vendor"] = "fengming" if area_scope == "cn" else "ares"
-        # Unconditional: turn detection is the single source of truth for the
-        # interaction language, so a vendor-level ``language`` would be silently
-        # discarded here. Do not add one to a vendor class — see
-        # docs/guides/preview-endpoint.md#the-vendor-class-is-not-the-whole-wire-shape.
         asr_config["language"] = self._field_value(turn_detection_config, "language")
         return asr_config
 

src/agora_agent/agentkit/agent_session.py

@@ -43,7 +43,6 @@
     normalize_preset_input,
     resolve_session_presets,
 )
-from .preview.client import create_preview_session_clients, required_preview_features
 from .token import _parse_numeric_uid, generate_convo_ai_token
 
 
@@ -182,24 +181,6 @@ def _require_agent_management(self) -> typing.Any:
             )
         return self._agent_management
 
-    def _bind_session_clients(self, features: typing.Sequence[str]) -> None:
-        """Pin this session to production or preview without mutating its client."""
-        if features:
-            self._agents, self._agent_management = create_preview_session_clients(
-                self._client, features
-            )
-            from .preview.client import PREVIEW_API_BASE_URL
-
-            self._api_base_url = PREVIEW_API_BASE_URL
-            return
-        self._agents = self._client.agents
-        self._agent_management = getattr(self._client, "agent_management", None)
-        self._api_base_url = (
-            self._client.get_current_url()
-            if hasattr(self._client, "get_current_url")
-            else None
-        )
-
     # ------------------------------------------------------------------
     # Internal helpers
     # ------------------------------------------------------------------
@@ -636,8 +617,6 @@ def start(self) -> str:
                 properties,
             )
 
-            self._bind_session_clients(required_preview_features(resolved_properties))
-
             if self._debug:
                 print("[Agora Debug] Starting agent session...")
                 if hasattr(self._client, "get_current_url"):
@@ -1003,8 +982,6 @@ async def start(self) -> str:
                 properties,
             )
 
-            self._bind_session_clients(required_preview_features(resolved_properties))
-
             if self._debug:
                 print("[Agora Debug] Starting agent session...")
                 if hasattr(self._client, "get_current_url"):